wav2vec2-base-finetuned-gtzan
This model is a fine-tuned version of facebook/wav2vec2-base on the GTZAN dataset. It achieves the following results on the evaluation set:
- Loss: 1.1430
- Accuracy: 0.76
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 3e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.2574 | 1.0 | 25 | 2.1793 | 0.445 |
| 1.9361 | 2.0 | 50 | 1.8937 | 0.475 |
| 1.7211 | 3.0 | 75 | 1.7034 | 0.54 |
| 1.5003 | 4.0 | 100 | 1.5038 | 0.63 |
| 1.3653 | 5.0 | 125 | 1.3770 | 0.7 |
| 1.2614 | 6.0 | 150 | 1.3169 | 0.69 |
| 1.1654 | 7.0 | 175 | 1.2444 | 0.725 |
| 1.0837 | 8.0 | 200 | 1.1828 | 0.755 |
| 1.0409 | 9.0 | 225 | 1.1549 | 0.755 |
| 1.0147 | 10.0 | 250 | 1.1430 | 0.76 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 1